© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49935
    Prev
    Next
    INDEX
    Explanations

    say words ending in "ive" or "comp"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _SOURCE
    -0.08
     abaf
    -0.08
    ource
    -0.07
     mentorship
    -0.07
     fontes
    -0.07
    ماه
    -0.07
    LETTER
    -0.07
    archy
    -0.07
     abi
    -0.07
     puestos
    -0.07
    POSITIVE LOGITS
    -comp
    0.16
     compuls
    0.15
     intrusive
    0.15
     repetitive
    0.13
     rituals
    0.13
     checking
    0.12
     unwanted
    0.12
     urges
    0.12
    重复
    0.12
    Comp
    0.12
    Activations Density 0.008%

    No Known Activations